When selecting the best checkpoint what is the recommended approach?
The validation set scores are produced based on accuracy, perplexity. If early stopping is not used could you advice how to select the best model? Do we need to check the BLEU score of the validation set as well, in addition to accuracy & perplexity?
When early stopping is Used, with both accuracy & perplexity the checkpoint given as best model, is not the model with highest accuracy? Is this acceptable? Or should we select by only going with accuracy?
What is the impact if we only go by early stopping with Accuracy?